Skim Logo
80,000 Hours15 hours ago
Godfather of AI: How To Make Safe Superintelligent AI – Yoshua Bengio
2:35:26
8H

Godfather of AI: How To Make Safe Superintelligent AI – Yoshua Bengio

Bengio: Coherence as a Training Objective — 80,000 Hours

From Godfather of AI: How To Make Safe Superintelligent AI – Yoshua Bengio. Category: Tech. Format: Interview. This is a single keypoint from the analysis.

Beyond predicting the next token, Scientist AI is trained for internal coherence, ensuring its explanations align with other strongly supported hypotheses. This mirrors scientific practice, where new explanations are rejected if they contradict existing evidence, fostering robust and reliable knowledge.

Impact: High. This introduces a powerful meta-learning objective, pushing AI towards a more holistic and scientifically rigorous understanding of the world, rather than mere pattern matching.

In the source video, this keypoint occurs from 01:37:31 to 01:38:18.

Sources in support: Rob Wiblin (Host)

For the full credibility analysis, key takeaways, and other keypoints from this video, see the full analysis on skim.

This keypoint analysis was generated by skim (skim.plus), an AI-powered content analysis platform by Credible AI.